A Dialogic Cognitive System With Externally Persisted State: A New Architecture of Human–AI Joint Thinking

The article proposes the concept of a dialogical cognitive system with an externally persistent state as a distinct architecture of joint thinking between humans and generative artificial intelligence. It examines situations in which an evolving reasoning process is preserved in an external dialogue and can be resumed after a temporal interruption without reconstructing the process from the beginning. The preserved state includes not only information, but also hypotheses, arguments, objections, connections, intermediate conclusions, and unresolved questions. Within such a system, generative AI functions not merely as a tool for obtaining or processing information, but also as a participant in the subsequent transformation of the preserved state of reasoning. The concept is related to research on extended and distributed cognition, cognitive offloading, transactive memory, and human–AI co-creativity. The article defines the principal elements of the proposed architecture and outlines directions for its further empirical investigation.